For the complete documentation index, see llms.txt. This page is also available as Markdown.
Cluster by Keyword
When you have a lot of related nodes with no grouping, the AI can automatically analyze them and create visual boundaries that group related items by theme or keyword. It's a fast way to bring structure to a messy board.
How to Use It
Select three or more nodes on the canvas.
Click the AI Adjust button in the selection toolbar.
Choose Cluster by keyword from the menu.
What Happens
The AI will:
Analyze the text content of the selected nodes.
Identify common themes or keywords.
Create visual group boundaries around related nodes, each with a descriptive label.
The resulting boundaries appear on the canvas just like any other group — you can rename them, resize them, or delete them afterwards if the AI's grouping isn't quite right.
When Cluster by Keyword Works Best
You have a long list of imported items (applications, capabilities, processes) and no idea where to start.
The node labels are meaningful — clustering is based on text, so "CRM System" clusters well, "App 1" does not.
You want a first-pass grouping that you'll refine manually.
When to Use Something Else
You already know how you want them grouped — just select the nodes and use Grouping to create a boundary manually.
You want connections, not boundaries — ask AI Chat to "Connect related nodes with dashed lines."
You only have a couple of nodes — clustering needs at least 3 and is more useful with 10+.
